Inference for Treatment Effects Conditional on Generalized Principal Strata using Instrumental Variables

TL;DR

This paper develops a comprehensive inference framework for treatment effects conditioned on generalized principal strata using instrumental variables, accommodating a broad class of parameters and assumptions with practical estimation methods.

Contribution

It introduces a novel approach to infer treatment effects based on generalized principal strata, including a characterization of the identified set and estimation techniques.

Findings

Framework includes many parameters from previous literature

Characterization of the identified set via linear systems

Proposed inference methods leverage recent theoretical results

Abstract

We propose a general approach for inference for a broad class of treatment effect parameters in a setting of a discrete valued treatment and instrument with a general outcome variable. The class of parameters considered are those that can be expressed as the expectation of a function of the response type conditional on a generalized principal stratum. Here, the response type refers to the vector of potential outcomes and potential treatments, and a generalized principal stratum is a set of possible values for the response type. In addition to instrument exogeneity, the main substantive restriction imposed rules out certain values for the response types in the sense that they are assumed to occur with probability zero. It is shown through a series of examples that this framework includes a wide variety of parameters and assumptions that have been considered in the previous literature. A key result in our analysis is a characterization of the identified set for such parameters under these assumptions in terms of existence of a non-negative solution to linear systems of equations with a special structure. We propose methods for inference exploiting this special structure and recent results in Fang et al. (2023).